Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 698 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.2634. Min Act: -0.1700

Data Index: 2006728 (Open Web Text)

Max Activating Token Index: 154

Text #1

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.2167. Min Act: -0.1700

Data Index: 6531047 (Open Web Text)

Max Activating Token Index: 223

Text #2

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.1726. Min Act: -0.1700

Data Index: 5724293 (Open Web Text)

Max Activating Token Index: 322

Text #3

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.1227. Min Act: -0.1700

Data Index: 6244018 (Open Web Text)

Max Activating Token Index: 347

Text #4

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.0941. Min Act: -0.1700

Data Index: 1498378 (Open Web Text)

Max Activating Token Index: 549

Text #5

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.0978. Min Act: -0.1700

Data Index: 1606491 (Open Web Text)

Max Activating Token Index: 103

Text #6

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.1018. Min Act: -0.1700

Data Index: 7385967 (Open Web Text)

Max Activating Token Index: 553

Text #7

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.0750. Min Act: -0.1700

Data Index: 4119216 (Open Web Text)

Max Activating Token Index: 380

Text #8

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.0693. Min Act: -0.1700

Data Index: 8530400 (Open Web Text)

Max Activating Token Index: 108

Text #9

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.0322. Min Act: -0.1700

Data Index: 2783934 (Open Web Text)

Max Activating Token Index: 763

Text #10

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.0400. Min Act: -0.1700

Data Index: 2924655 (Open Web Text)

Max Activating Token Index: 676

Text #11

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.0255. Min Act: -0.1700

Data Index: 3080575 (Open Web Text)

Max Activating Token Index: 568

Text #12

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.0236. Min Act: -0.1700

Data Index: 5333135 (Open Web Text)

Max Activating Token Index: 765

Text #13

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.0146. Min Act: -0.1700

Data Index: 5994823 (Open Web Text)

Max Activating Token Index: 816

Text #14

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.0325. Min Act: -0.1700

Data Index: 3842475 (Open Web Text)

Max Activating Token Index: 223

Text #15

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.0124. Min Act: -0.1700

Data Index: 3141758 (Open Web Text)

Max Activating Token Index: 990

Text #16

Max Range: 4.2634. Min Range: -4.2634

Max Act: 3.9838. Min Act: -0.1700

Data Index: 2398408 (Open Web Text)

Max Activating Token Index: 813

Text #17

Max Range: 4.2634. Min Range: -4.2634

Max Act: 3.9727. Min Act: -0.1700

Data Index: 7395898 (Open Web Text)

Max Activating Token Index: 532

Text #18

Max Range: 4.2634. Min Range: -4.2634

Max Act: 3.9718. Min Act: -0.1700

Data Index: 109186 (Open Web Text)

Max Activating Token Index: 345

Text #19

Max Range: 4.2634. Min Range: -4.2634

Max Act: 3.9848. Min Act: -0.1700

Data Index: 3681758 (Open Web Text)

Max Activating Token Index: 536